Workspace Qdrant MCP server

This is a helper that gives your AI assistant a memory for your project. It reads your code and documents, keeps them in a searchable store, and lets the AI look things up quickly. It is handy if you work on a codebase with ChatGPT or Claude and keep re-explaining the same things.

What this MCP server does

You ask your AI a question about your project, like where a function lives or how something works. The AI uses this helper to search an index of your code and documents. The helper talks to a local search store called Qdrant, which holds the indexed content. It can also save new findings, notes, or reference documents so they are there next time. You get back answers, file lists, or saved notes right in the chat.

Click to zoom

What you can do with it

• Search your project's code and docs by meaning, not just exact words
• Find exact strings or patterns in your files
• List files and folder structure in a project
• Save notes, findings, or design reasons for later sessions
• Store external reference docs so they are searchable next to your code
• Keep persistent rules that the AI follows across sessions
• Look up a document directly by its ID or a filter

Try asking your AI

• “Search my project for where user login is handled”
• “Find every file that mentions the word invoice”
• “List the files in the src folder as a summary”
• “Save this note: we chose Postgres because of the reporting needs”

What it gives back to you

You get answers in plain chat: short summaries, lists of matching files, or snippets from your code and notes. When you save something, the AI confirms it stored the note. When you search, it shows the most relevant matches with a bit of context. Over time, the AI can pull up things from earlier sessions that you would otherwise have to repeat.

Before you start

Who it's for

Developers and technical teams who use an AI assistant on a codebase and want it to remember context between sessions.